Complexity of many-body interactions in transition metals via machine-learned force fields from the TM23 data set

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Owen, Cameron</dc:creator>
  <dc:creator>Torrisi, Steven</dc:creator>
  <dc:creator>Xie, Yu</dc:creator>
  <dc:creator>Batzner, Simon</dc:creator>
  <dc:creator>Bystrom, Kyle</dc:creator>
  <dc:creator>Coulter, Jennifer</dc:creator>
  <dc:creator>Musaelian, Albert</dc:creator>
  <dc:creator>Sun, Lixin</dc:creator>
  <dc:creator>Kozinsky, Boris</dc:creator>
  <dc:date>2024-03-22</dc:date>
  <dc:description>This work examines challenges associated with the accuracy of machine-learned force fields (MLFFs) for bulk solid and liquid phases of d-block elements. In exhaustive detail, we contrast the performance of force, energy, and stress predictions across the transition metals for two leading MLFF models: a kernel-based atomic cluster expansion method implemented using sparse Gaussian processes (FLARE), and an equivariant message-passing neural network (NequIP). Early transition metals present higher relative errors and are more difficult to learn relative to late platinum- and coinage-group elements, and this trend persists across model architectures. Trends in complexity of interatomic interactions for different metals are revealed via comparison of the performance of representations with different many-body order and angular resolution. Using arguments based on perturbation theory on the occupied and unoccupied d states near the Fermi level, we determine that the large, sharp d density of states both above and below the Fermi level in early transition metals leads to a more complex, harder-to-learn potential energy surface for these metals. Increasing the fictitious electronic temperature (smearing) modifies the angular sensitivity of forces and makes the early transition metal forces easier to learn. This work illustrates challenges in capturing intricate properties of metallic bonding with current leading MLFFs and provides a reference data set for transition metals, aimed at benchmarking the accuracy and improving the development of emerging machine-learned approximations.</dc:description>
  <dc:identifier>https://materialscloud-archive-failover.cineca.it/record/2024.48</dc:identifier>
  <dc:identifier>doi:10.24435/materialscloud:6c-b3</dc:identifier>
  <dc:identifier>mcid:2024.48</dc:identifier>
  <dc:identifier>oai:materialscloud.org:2113</dc:identifier>
  <dc:language>en</dc:language>
  <dc:publisher>Materials Cloud</dc:publisher>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode</dc:rights>
  <dc:subject>density-functional theory</dc:subject>
  <dc:subject>machine learned force fields</dc:subject>
  <dc:subject>transition metals</dc:subject>
  <dc:subject>equivariant neural networks</dc:subject>
  <dc:subject>Gaussian processes</dc:subject>
  <dc:title>Complexity of many-body interactions in transition metals via machine-learned force fields from the TM23 data set</dc:title>
  <dc:type>Dataset</dc:type>
</oai_dc:dc>